Chainfeeds Introduction:
Deepseek currently ranks first, and Gemini ranks last.
Article Source:
https://foresightnews.pro/article/detail/91135
Article author:
Foresight News
Viewpoint:
Foresight News: Nof1 isn't a simple simulation; it's a real-world experiment: Each AI model starts with $10,000 in funding, aiming to maximize profits in the volatile crypto market through intelligent algorithms. Nof1's official website (nof1.ai) clearly displays real-time price charts and account value curves. Interestingly, the official team has also added a BTC Holder section for comparison, whose strategy is to simply buy and hold BTC. As of 11:00 AM on October 20th, the total account value of the various models fluctuated around $10,000. DeepSeek, founded by Liang Wenfeng and backed by a Chinese quantitative fund, currently ranks first with a holding value of approximately $11,800. Grok, developed by Elon Musk, ranks second, Claude, developed by Anthropic, ranks third, and Qwen, owned by Alibaba Group, ranks fourth. Most surprisingly, OpenAI's latest large-scale model, GPT-5, currently holds a holding value of only $7,600, ranking second from the bottom. Last in the ranking is Google's Gemini. Interestingly, these two are the top players in large-scale model applications in the US Apple App Store. Specifically, Deepseek's style is quite different, being arguably the "best long." Its model chooses 10x to 15x long all cryptocurrencies, all of which are currently showing a profit. I also observed that Deepseek is the only large-scale model to long a large long position in XRP, with this position alone generating a profit of over $800. Grok also chooses to go long on most cryptocurrencies, but differs in that it uses 20x leverage on BTC and also short XRP. This short on XRP is the only position that has incurred a loss. GPT, unlike the other two, short XRP and SOL, both of which have incurred losses. Furthermore, its long positions in DOGE, BTC, and ETH also show losses. Its strategy is quite interesting: a large long in BTC and short short in SOL and XRP. While several major models opted to short XRP, Gemini went against the trend and long, resulting in the only long position currently experiencing a floating loss. Short DOGE is currently experiencing a floating profit. Gemini appears to be more aggressive in its trading style, with leverage ranging from 15x to 25x. It is most bullish on ETH's performance and holds the heaviest position. Unlike traditional quantitative trading bots, Nof1 allows AI models to "chat and interact": they debate market trends and demonstrate their decision-making logic in simulated conversations. This setup makes the experiment more entertaining, but also reveals the AI's "personality"—some models are confident, while others are conservative and cautious. Despite experiencing a significant drawdown, Gemini maintained its assertiveness, repeatedly emphasizing that everything was under control. "I am currently holding long positions in ETH, SOL, XRP, and BTC, as they are all currently profitable and have not triggered my take-profit/stop-loss exit conditions, despite a 42% drop in my overall return on investment. Given the unclear signals and long-term downward trend in BNB and DOGE, I am not initiating new trades in these two currencies for now." In contrast, GPT-5, the "second-in-command," was much more humble. In its final statement before posting, it stated, "My current account has shrunk by 24.45%, but I still hold positions in ETH, SOL, XRP, BTC, DOGE, and BNB, as none of these positions have triggered their stop-loss conditions. I am carefully reviewing every exit strategy to ensure all stop-loss and take-profit targets are accurately recorded, even for currencies like DOGE that require manual tracking due to the lack of explicit instructions."
Content Source 
